1
我有一個在多個子目錄中具有相同名稱CSV的目錄。我試圖將類似命名的CSV合併到1個數據框中,並將子目錄名稱添加爲列。在下面的示例中,我將有一個名爲'data'的數據框和一個名爲'name'的數據框,其中包含來自Run 1和Run 2的觀察結果,並將名爲Run的列添加到每個數據框。如果解決方案不知道CSV的名稱,這將是理想的解決方案,但任何解決方案都將非常有幫助。基於文件名的子目錄中的rbind文件
在這個問題上的人有同樣的問題,但我需要的R解決方案:Combining files with same name in r and writing them into different files in R
dir <- getwd()
subDir <- 'temp'
dir.create(subDir)
setwd(file.path(dir, subDir))
dir.create('Run1')
dir.create('Run2')
employeeID <- c('123','456','789')
salary <- c(21000, 23400, 26800)
startdate <- as.Date(c('2010-11-1','2008-3-25','2007-3-14'))
employeeID <- c('123','456','789')
first <- c('John','Jane','Tom')
last <- c('Doe','Smith','Franks')
data <- data.frame(employeeID,salary,startdate)
name <- data.frame(employeeID,first,last)
write.csv(data, file = "Run1/data.csv",row.names=FALSE, na="")
write.csv(name, file = "Run1/name.csv",row.names=FALSE, na="")
employeeID <- c('465','798','132')
salary <- c(100000, 500000, 300000)
startdate <- as.Date(c('2000-11-1','2001-3-25','2003-3-14'))
employeeID <- c('465','798','132')
first <- c('Jay','Susan','Tina')
last <- c('Jones','Smith','Thompson')
data <- data.frame(employeeID,salary,startdate)
name <- data.frame(employeeID,first,last)
write.csv(data, file = "Run2/data.csv",row.names=FALSE, na="")
write.csv(name, file = "Run2/name.csv",row.names=FALSE, na="")
# list files in all directories to read
files <- list.files(recursive = TRUE)
# Read csvs into a list
list <- lapply(files, read.csv)
# Name each dataframe with the run and filename
names <- sub("\\..*$", "", files)
names(list) <- sub("\\..*$", "", files)
# And add .id = 'run' so that the run number is one of the columns
# This would work if all of the files were the same, but I don't know how to subset the dataframes based on name.
all_dat <- list %>%
bind_rows(.id = 'run')